Artificial Expert Intelligence through PAC-reasoning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shalev-Shwartz, Shai, Shashua, Amnon, Beniamini, Gal, Levine, Yoav, Sharir, Or, Wies, Noam, Ben-Shaul, Ido, Nussbaum, Tomer, Peled, Shir Granot
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917855652478976
author Shalev-Shwartz, Shai
Shashua, Amnon
Beniamini, Gal
Levine, Yoav
Sharir, Or
Wies, Noam
Ben-Shaul, Ido
Nussbaum, Tomer
Peled, Shir Granot
author_facet Shalev-Shwartz, Shai
Shashua, Amnon
Beniamini, Gal
Levine, Yoav
Sharir, Or
Wies, Noam
Ben-Shaul, Ido
Nussbaum, Tomer
Peled, Shir Granot
contents Artificial Expert Intelligence (AEI) seeks to transcend the limitations of both Artificial General Intelligence (AGI) and narrow AI by integrating domain-specific expertise with critical, precise reasoning capabilities akin to those of top human experts. Existing AI systems often excel at predefined tasks but struggle with adaptability and precision in novel problem-solving. To overcome this, AEI introduces a framework for ``Probably Approximately Correct (PAC) Reasoning". This paradigm provides robust theoretical guarantees for reliably decomposing complex problems, with a practical mechanism for controlling reasoning precision. In reference to the division of human thought into System 1 for intuitive thinking and System 2 for reflective reasoning~\citep{tversky1974judgment}, we refer to this new type of reasoning as System 3 for precise reasoning, inspired by the rigor of the scientific method. AEI thus establishes a foundation for error-bounded, inference-time learning.
format Preprint
id arxiv_https___arxiv_org_abs_2412_02441
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Artificial Expert Intelligence through PAC-reasoning
Shalev-Shwartz, Shai
Shashua, Amnon
Beniamini, Gal
Levine, Yoav
Sharir, Or
Wies, Noam
Ben-Shaul, Ido
Nussbaum, Tomer
Peled, Shir Granot
Artificial Intelligence
Computation and Language
Machine Learning
Artificial Expert Intelligence (AEI) seeks to transcend the limitations of both Artificial General Intelligence (AGI) and narrow AI by integrating domain-specific expertise with critical, precise reasoning capabilities akin to those of top human experts. Existing AI systems often excel at predefined tasks but struggle with adaptability and precision in novel problem-solving. To overcome this, AEI introduces a framework for ``Probably Approximately Correct (PAC) Reasoning". This paradigm provides robust theoretical guarantees for reliably decomposing complex problems, with a practical mechanism for controlling reasoning precision. In reference to the division of human thought into System 1 for intuitive thinking and System 2 for reflective reasoning~\citep{tversky1974judgment}, we refer to this new type of reasoning as System 3 for precise reasoning, inspired by the rigor of the scientific method. AEI thus establishes a foundation for error-bounded, inference-time learning.
title Artificial Expert Intelligence through PAC-reasoning
topic Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2412.02441